该文在考虑过程神经网络对时间聚合运算的复杂性的基础上，提出了一种基于函数正交基展开的学习算法。
In consideration of the complexity of the aggregation operation of time in process neural networks, a new learning algorithm based on function orthogonal basis expansion is proposed.
本论文围绕二维相关光谱技术在多个亲水性聚合物研究中的应用而展开。
This thesis centers on the application of two-dimensional infrared and near-infrared correlation spectroscopy(2DCOS) on the study of several hydrophilic polymers.
在输入空间中引入一组函数正交基，将输入函数和网络权函数表示为该组正交基的展开形式，利用基函数的正交性简化过程神经元聚合运算。
By introducing a group of function orthogonal basis into the input space, the input functions and the network weight functions are expressed in the expansion form.
应用推荐